English

Toward Speech Separation in The Pre-Cocktail Party Problem with TasTas

Audio and Speech Processing 2023-06-26 v4 Sound

Abstract

In this note, we propose to use TasTas \cite{shi2020speech} for the end-to-end approach to monaural speech separation in the pre-cocktail party problem. Our experiments on the public WSJ0-5mix data corpus results in 10.41dB SDR improvement. If online voice data remixing augmentation \cite{zeghidour2020wavesplit} is adopted in training, an 11.14dB SDR improvement can be achieved. We have open-sourced our re-implementation of the DPRNN-TasNet in https://github.com/ShiZiqiang/dual-path-RNNs-DPRNNs-based-speech-separation, and our TasTas is realized based on this implementation of DPRNN-TasNet, it is believed that the results in this paper can be reproduced with ease.

Keywords

Cite

@article{arxiv.2009.03692,
  title  = {Toward Speech Separation in The Pre-Cocktail Party Problem with TasTas},
  author = {Ziqiang Shi and Jiqing Han},
  journal= {arXiv preprint arXiv:2009.03692},
  year   = {2023}
}

Comments

arXiv admin note: substantial text overlap with arXiv:1902.04891